We're hiring on behalf of a client building a next-gen AI platform for regulatory automation. They’re urgently looking for a GenAI Architect to lead the design and deployment of multi-agent systems and integrate cutting-edge LLM capabilities into their SaaS product.

You’ll be focused on designing autonomous AI agents that can reason over complex regulatory content and automate key compliance workflows for enterprise customers. This includes building out retrieval-augmented generation pipelines, memory layers, and orchestration logic for goal-directed agent behaviour.
The role is remote-first (UK, Ireland, or Europe).

Core responsibilities:
  • Designing end-to-end GenAI architecture including RAG pipelines, graph-based memory, vector search, and LLM agent orchestration
  • Deploying solutions using frameworks like LangChain, Autogen, LlamaIndex, LangGraph
  • Driving AI strategy and performance evaluation with MLOps tools (Langsmith, MLflow, SageMaker)
  • Leading system integration, roadmap definition, and stakeholder collaboration
You’ll work across product, engineering, and AI to bring scalable features into production. If you’ve built GenAI systems in production and enjoy working with advanced agent frameworks, I’d be happy to share more.
 If you're interested, feel free to respond with your most up-to-date resume/CV and I'll be in touch to discuss your profille.